fix: import

notebooks/official/automl/get_started_automl_training.ipynb

@@ -168,21 +168,10 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
         "# Install the packages\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
-        "! pip3 install --upgrade google-cloud-storage $USER_FLAG -q"
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                 google-cloud-storage "
       ]
     },
     {
@@ -191,64 +180,38 @@
         "id": "restart"
       },
       "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "### Colab only: Uncomment the following cell to restart the kernel"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "project_id"
+        "id": "yfEglUHQk9S3"
       },
       "source": [
         "## Before you begin\n",
         "\n",
-        "### Set up your Google Cloud project\n",
+        "### Set your project ID\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage_component).\n",
-        "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5aee4379e8e5"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
@@ -259,33 +222,10 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_gcloud_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
@@ -296,16 +236,7 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -316,95 +247,65 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "timestamp"
-      },
-      "source": [
-        "#### Timestamp\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "timestamp"
-      },
-      "outputs": [],
-      "source": [
-        "from datetime import datetime\n",
-        "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "3ffa6b6c7cdb"
+        "id": "gcp_authenticate"
       },
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated.\n",
         "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
-        "\n",
-        "1. **Click Create service account**.\n",
-        "\n",
-        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
-        "\n",
-        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
-        "\n",
-        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "2b72272258fc"
+        "id": "ce6043da7b33"
       },
       "outputs": [],
       "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = False\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        IS_COLAB = True\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
       ]
     },
     {
@@ -415,11 +316,7 @@
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
@@ -430,21 +327,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
-        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -467,26 +350,6 @@
         "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -501,12 +364,14 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 1,
+      "execution_count": null,
       "metadata": {
         "id": "import_aip:mbsdk"
       },
       "outputs": [],
       "source": [
+        "import sys\n",
+        "\n",
         "import google.cloud.aiplatform as aiplatform"
       ]
     },
@@ -791,7 +656,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.ImageDataset.create(\n",
-        "    display_name=\"flowers_\" + TIMESTAMP,\n",
+        "    display_name=\"flowers\",\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.image.single_label_classification,\n",
         ")\n",
@@ -839,7 +704,7 @@
       "outputs": [],
       "source": [
         "dag = aiplatform.AutoMLImageTrainingJob(\n",
-        "    display_name=\"flowers_\" + TIMESTAMP,\n",
+        "    display_name=\"flowers\",\n",
         "    prediction_type=\"classification\",\n",
         "    multi_label=False,\n",
         "    model_type=\"MOBILE_TF_LOW_LATENCY_1\",\n",
@@ -894,7 +759,7 @@
       "source": [
         "model = dag.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"flowers_\" + TIMESTAMP,\n",
+        "    model_display_name=\"flowers\",\n",
         "    training_fraction_split=0.8,\n",
         "    validation_fraction_split=0.1,\n",
         "    test_fraction_split=0.1,\n",
@@ -1037,7 +902,7 @@
         "\n",
         "# Download the test image in bytes format\n",
         "storage_client = storage.Client(project=PROJECT_ID)\n",
-        "bucket = storage_client.bucket(bucket_name=BUCKET_NAME)\n",
+        "bucket = storage_client.bucket(bucket_name=BUCKET_URI[5:])\n",
         "test_content = bucket.get_blob(\"test.jpg\").download_as_bytes()\n",
         "\n",
         "# The format of each instance should conform to the deployed model's prediction input schema.\n",
@@ -1306,9 +1171,9 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.TabularDataset.create(\n",
-        "    display_name=\"gsod_\" + TIMESTAMP,\n",
+        "    display_name=\"gsod\",\n",
         "    bq_source=[IMPORT_FILE],\n",
-        "    labels={\"user_metadata\": BUCKET_NAME},\n",
+        "    labels={\"user_metadata\": BUCKET_URI[5:]},\n",
         ")\n",
         "\n",
         "label_column = \"mean_temp\"\n",
@@ -1376,7 +1241,7 @@
       "outputs": [],
       "source": [
         "dag = aiplatform.AutoMLTabularTrainingJob(\n",
-        "    display_name=\"gsod_\" + TIMESTAMP,\n",
+        "    display_name=\"gsod\",\n",
         "    optimization_prediction_type=\"regression\",\n",
         "    optimization_objective=\"minimize-rmse\",\n",
         "    column_transformations=TRANSFORMATIONS,\n",
@@ -1419,7 +1284,7 @@
       "source": [
         "model = dag.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"gsod_\" + TIMESTAMP,\n",
+        "    model_display_name=\"gsod\",\n",
         "    training_fraction_split=0.8,\n",
         "    validation_fraction_split=0.1,\n",
         "    test_fraction_split=0.1,\n",
@@ -1845,7 +1710,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.TextDataset.create(\n",
-        "    display_name=\"happydb_\" + TIMESTAMP,\n",
+        "    display_name=\"happydb\",\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.text.single_label_classification,\n",
         ")\n",
@@ -1885,7 +1750,7 @@
       "outputs": [],
       "source": [
         "dag = aiplatform.AutoMLTextTrainingJob(\n",
-        "    display_name=\"happydb_\" + TIMESTAMP,\n",
+        "    display_name=\"happydb\",\n",
         "    prediction_type=\"classification\",\n",
         "    multi_label=False,\n",
         ")\n",
@@ -1924,7 +1789,7 @@
       "source": [
         "model = dag.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"happydb_\" + TIMESTAMP,\n",
+        "    model_display_name=\"happydb\",\n",
         "    training_fraction_split=0.8,\n",
         "    validation_fraction_split=0.1,\n",
         "    test_fraction_split=0.1,\n",
@@ -2304,7 +2169,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.VideoDataset.create(\n",
-        "    display_name=\"human_motion_\" + TIMESTAMP,\n",
+        "    display_name=\"human_motion\",\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.video.classification,\n",
         ")\n",
@@ -2342,7 +2207,7 @@
       "outputs": [],
       "source": [
         "dag = aiplatform.AutoMLVideoTrainingJob(\n",
-        "    display_name=\"human_motion_\" + TIMESTAMP,\n",
+        "    display_name=\"human_motion\",\n",
         "    prediction_type=\"classification\",\n",
         ")\n",
         "\n",
@@ -2379,7 +2244,7 @@
       "source": [
         "model = dag.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"human_motion_\" + TIMESTAMP,\n",
+        "    model_display_name=\"human_motion\",\n",
         "    training_fraction_split=0.8,\n",
         "    test_fraction_split=0.2,\n",
         ")"